http://repositorio.ufc.br/handle/riufc/484 2026-07-30T00:18:14Z http://repositorio.ufc.br/handle/riufc/87102 Título: Discriminant Independent Vector Analysis Autor(es): Maia, Marília Magalhães Abstract: With the rapid advancement of technology and the accelerated growth in data production, Blind Source Separation (BSS) methods have gained increasing relevance due to their broad applicability across diverse domains. In scenarios where multiple data modalities are mixed and the objective is to recover the original underlying sources, techniques capable of exploiting relationships among them become essential, particularly in representation and classification tasks. The traditional method for handling such multimodal data is Independent Vector Analysis (IVA); however, its non-discriminative nature limits its performance when source separation is directly linked to classification objectives. In this context, this work introduces Discriminant Independent Vector Analysis (DIVA), a supervised extension of IVA constructed through the incorporation of Fisher’s Linear Discriminant (FLD) criterion into the IVA framework. The resulting method aims to estimate independent sources that, in addition to satisfying statistical independence, maximize class separability, making it particularly suitable for binary classification problems. The proposed model was implemented based on IVA-G, a widely established formulation in the literature. To evaluate the performance of DIVA-G, a Support Vector Machine (SVM) classifier was employed in a semi-supervised setting, using the F1-score as the primary evaluation metric. Experiments with synthetic datasets enabled the identification of statistical characteristics that favor the method, demonstrating consistent and superior performance compared with other IVA-derived algorithms. Subsequently, the real-world datasets NSL-KDD and MediaEval2016 were used to investigate the behavior of the method in complex and noisy scenarios. The results indicate satisfactory performance, stability, and reliability, suggesting that DIVA-G is a promising approach for discriminative source separation and warrants further, more in-depth investigation. Tipo: Dissertação 2026-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86964 Título: A multi-agent traceable semantic graph architecture for digital forensic knowledge representation and relational inference Autor(es): Monteiro, Marcos José Alves de Barros Abstract: Digital forensic investigations increasingly depend on the interpretation of heterogeneous evidence recovered from multiple computational artifacts. Although extraction tools have advanced considerably, connecting recovered traces to investigative reasoning remains a technical challenge, particularly when provenance and traceability must be preserved for later examination. This dissertation introduces a graph-centered multi-agent framework for organizing digital forensic evidence as a structured semantic representation linked to artifacts extracted from forensic disk images. The framework connects entities, semantic relations, provenance metadata, and investigative hypotheses within a unified Digital Forensic Knowledge Graph, enabling relational inference under incomplete-evidence conditions. Experimental evaluation showed 73.3% concept recovery, 73.3% semantic relation recovery, 57.0% hypothesis coverage, and full traceability coverage for evidentiary relations. Among the evaluated inference models, node2vec_b f s_ppmi_negative_l2 achieved the strongest overall performance under controlled perturbation settings. The findings show that graph-based semantic representation can support forensic reasoning while maintaining explicit linkage between inferred relations and traceable digital evidence. Tipo: Dissertação 2026-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86946 Título: Análise de falhas de coprocessadores compartilhados em um MPSoC para estender o ISA RISC-V Autor(es): Reis, Jorge Luiz Costa Abstract: Reduced Instruction Set (RISC) architectures optimize a complex ISA by implementing only the most frequently used instructions in hardware. However, the application execution time significantly increases when executing heavily used instructions in software. One technique that optimizes the trade-off of implementation cost and execution time is the use of a Multiprocessor System-on-Chip (MPSoC), in which processors extend their ISA by sharing coprocessors that implement lesser-used instructions. In this work the impact of shared coprocessor failures on two RISC-V MPSoC architectures is analyzed. In the first phase, we evaluated these architectures using two image processing applications and four different models of failure rates in terms of power dissipation, energy consumption, area consumption, maximum operating frequency, and execution time. The experiments in this phase show a maximum increase of 16% in execution time for the application with a lower percentage of instructions executed on the coprocessor. For the application with the highest rate of coprocessor use, the execution time does not increase significantly in the proposed architectural configurations for the MPSoC after the first failure scenario. For the second phase of the work, the MPSoC was expanded to allow testing with six different models and four failure rates. The experiments in this phase showed a 34% increase in execution time for the application with a lower rate of instructions executed on the coprocessor. For the other application, the increase reached 92% in execution time. Tipo: Dissertação 2023-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/86941 Título: Channel estimation and tracking for IRS-assisted MIMO communications using tensor modeling Autor(es): Benício, Kenneth Brenner dos Anjos Abstract: Over the last few years, intelligent reflecting surface (IRS)-assisted networks have been extensively studied as one of the possible technologies to be deployed in developing sixth generation (6G) wireless networks to achieve its vital system integration and data transmission features. In this dissertation, we use tensor algebra to model and solve channel estimation and tracking problems using parametric models in the context of IRS-assisted networks. The dissertation is divided into three parts. First, we consider an unstructured estimation of (quasi)- static channels using a Tucker modeling of the reflected pilot signals. The problem is solved using either an iterative alternating least squares (ALS) algorithm or a closed-form higher order singular value decomposition (HOSVD) algorithm. In the second part, to acquire an estimation of the concatenated channel, we formulate a parameter estimation for a hybrid scenario where the channel between the base station (BS) and the IRS is static, while the channel between the IRS and the user equipment (UE) is time-varying. In the third part, we extend our previously proposed model to a more general scenario, where the overall UE-IRS-BS channel has a two-time scale double time-varying structure. In this case, the receiver processing has two stages. The first stage estimates the spatial signatures of the involved channels based on a 4th-order constrained PARAFAC model. In contrast, the second stage performs channel tracking and data detection by exploiting a Tucker model for the received data tensor. The performance of the proposed methods is also studied numerically in terms of normalized mean square error (NMSE), computational complexity, and bit error ratio (BER). Tipo: Dissertação 2023-01-01T00:00:00Z